© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 6127
    Prev
    Next
    INDEX
    Explanations

    sentences describing tools and how they are used, especially with specific instructions and measurements

    oai_token-act-pair · gemini-2.0-flash

    fasteners and mechanics

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nut
    -1.51
     screw
    -1.45
     Nut
    -1.40
     Screw
    -1.36
    Nut
    -1.33
     nail
    -1.32
     nuts
    -1.27
    screw
    -1.23
    nut
    -1.23
     Nail
    -1.22
    POSITIVE LOGITS
    Conway
    0.49
    GraphicsUnit
    0.49
     ModelExpression
    0.48
     contraband
    0.48
     crdi
    0.46
    RTSC
    0.44
     innocence
    0.44
     Conway
    0.44
    RemoveField
    0.44
    Allister
    0.43
    Activations Density 1.307%

    No Known Activations